<![CDATA[The rapid growth of digital text information makes it crystal clear that there is a need for automated tools that summarize text for rapid retrieval. Extractive methods employed include LexRank, Latent Dirichlet Allocation (LDA), and Maximal Marginal Relevance (MMR), and the study aimed at enhancing the quality of Indonesian text summaries with more than just regular LexRank. In this study, the role of LexRank was to assist in selecting meaningful sentences with centricity to the center of the graphs, while the role of LDA was to ensure that the sentences were topically relevant. The strength of MMR is maintaining the document's relevance and diversity, which reduces redundancy in the summaries. Summaries from two publicly available datasets, IndoSum and Liputan6, containing texts in Bahasa Indonesia, were analyzed at 30% and 50% compression levels and graded using ROUGE (ROUGE-1, ROUGE-2, ROUGE-L F1 score) measurements. Analysis of 5000 articles per dataset showed that the implementation of LexRank and LDA together with MMR resulted in a greater average ROUGE score than when using standard LexRank, irrespective of the set compression levels and across both datasets, demonstrating the effectiveness of the approach to enhance summary quality. The improvements recorded are most significant in ROUGE-1 and ROUGE-2, which indicates that these combination approaches can produce more informative and relevant summaries while preserving sentence-level diversity, which deepens the understanding of the information presented in the summary.]]>
Copyrights © 2026
